Instructions to use gn00029914/Gemma-3-TAIDE-12b-Chat-2602-Q3_K_L-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use gn00029914/Gemma-3-TAIDE-12b-Chat-2602-Q3_K_L-GGUF with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("image-text-to-text", model="gn00029914/Gemma-3-TAIDE-12b-Chat-2602-Q3_K_L-GGUF")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
pipe(text=messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("gn00029914/Gemma-3-TAIDE-12b-Chat-2602-Q3_K_L-GGUF", dtype="auto")

llama-cpp-python

How to use gn00029914/Gemma-3-TAIDE-12b-Chat-2602-Q3_K_L-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="gn00029914/Gemma-3-TAIDE-12b-Chat-2602-Q3_K_L-GGUF",
	filename="Gemma-3-TAIDE-12b-Chat-2602-Q3_K_L.gguf",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": [
				{
					"type": "text",
					"text": "Describe this image in one sentence."
				},
				{
					"type": "image_url",
					"image_url": {
						"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
					}
				}
			]
		}
	]
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use gn00029914/Gemma-3-TAIDE-12b-Chat-2602-Q3_K_L-GGUF with llama.cpp:

Install (macOS, Linux)

curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf gn00029914/Gemma-3-TAIDE-12b-Chat-2602-Q3_K_L-GGUF:Q3_K_L
# Run inference directly in the terminal:
llama cli -hf gn00029914/Gemma-3-TAIDE-12b-Chat-2602-Q3_K_L-GGUF:Q3_K_L

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf gn00029914/Gemma-3-TAIDE-12b-Chat-2602-Q3_K_L-GGUF:Q3_K_L
# Run inference directly in the terminal:
llama cli -hf gn00029914/Gemma-3-TAIDE-12b-Chat-2602-Q3_K_L-GGUF:Q3_K_L

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf gn00029914/Gemma-3-TAIDE-12b-Chat-2602-Q3_K_L-GGUF:Q3_K_L
# Run inference directly in the terminal:
./llama-cli -hf gn00029914/Gemma-3-TAIDE-12b-Chat-2602-Q3_K_L-GGUF:Q3_K_L

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf gn00029914/Gemma-3-TAIDE-12b-Chat-2602-Q3_K_L-GGUF:Q3_K_L
# Run inference directly in the terminal:
./build/bin/llama-cli -hf gn00029914/Gemma-3-TAIDE-12b-Chat-2602-Q3_K_L-GGUF:Q3_K_L

Use Docker

docker model run hf.co/gn00029914/Gemma-3-TAIDE-12b-Chat-2602-Q3_K_L-GGUF:Q3_K_L

LM Studio
Jan

vLLM

How to use gn00029914/Gemma-3-TAIDE-12b-Chat-2602-Q3_K_L-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "gn00029914/Gemma-3-TAIDE-12b-Chat-2602-Q3_K_L-GGUF"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "gn00029914/Gemma-3-TAIDE-12b-Chat-2602-Q3_K_L-GGUF",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker

docker model run hf.co/gn00029914/Gemma-3-TAIDE-12b-Chat-2602-Q3_K_L-GGUF:Q3_K_L

SGLang

How to use gn00029914/Gemma-3-TAIDE-12b-Chat-2602-Q3_K_L-GGUF with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "gn00029914/Gemma-3-TAIDE-12b-Chat-2602-Q3_K_L-GGUF" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "gn00029914/Gemma-3-TAIDE-12b-Chat-2602-Q3_K_L-GGUF",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "gn00029914/Gemma-3-TAIDE-12b-Chat-2602-Q3_K_L-GGUF" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "gn00029914/Gemma-3-TAIDE-12b-Chat-2602-Q3_K_L-GGUF",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Ollama
How to use gn00029914/Gemma-3-TAIDE-12b-Chat-2602-Q3_K_L-GGUF with Ollama:
```
ollama run hf.co/gn00029914/Gemma-3-TAIDE-12b-Chat-2602-Q3_K_L-GGUF:Q3_K_L
```

Unsloth Studio

How to use gn00029914/Gemma-3-TAIDE-12b-Chat-2602-Q3_K_L-GGUF with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for gn00029914/Gemma-3-TAIDE-12b-Chat-2602-Q3_K_L-GGUF to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for gn00029914/Gemma-3-TAIDE-12b-Chat-2602-Q3_K_L-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for gn00029914/Gemma-3-TAIDE-12b-Chat-2602-Q3_K_L-GGUF to start chatting

Atomic Chat new
Docker Model Runner
How to use gn00029914/Gemma-3-TAIDE-12b-Chat-2602-Q3_K_L-GGUF with Docker Model Runner:
```
docker model run hf.co/gn00029914/Gemma-3-TAIDE-12b-Chat-2602-Q3_K_L-GGUF:Q3_K_L
```

Lemonade

How to use gn00029914/Gemma-3-TAIDE-12b-Chat-2602-Q3_K_L-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull gn00029914/Gemma-3-TAIDE-12b-Chat-2602-Q3_K_L-GGUF:Q3_K_L

Run and chat with the model

lemonade run user.Gemma-3-TAIDE-12b-Chat-2602-Q3_K_L-GGUF-Q3_K_L

List all available models

lemonade list

Gemma-3-TAIDE-12b-Chat-2602 (Q3_K_L)

本模型是由 TAIDE 基於 Google Gemma-3-12b 進行微調的繁體中文強化版本。此 GGUF 版本量化採用 audreyt 的 Gemma-3-TAIDE-12b-Chat-2602-F16.gguf 及 Bartowski 的 mmproj-google_gemma-3-12b-it-bf16.gguf。(Accessed May 4, 2026) 並收藏 mradermacher 的 gemma-3-12b-it-qat-q4_0-unquantized.mmproj-Q8_0.gguf 作為 mmproj 檔的可選項。(Accessed May 6, 2026)

🚀 llama-cli 教學

# 下載模型檔案
hf download gn00029914/Gemma-3-TAIDE-12b-Chat-2602-Q3_K_L-GGUF:Q3_K_L

# 執行對話 (含視覺)
llama-cli -hf gn00029914/Gemma-3-TAIDE-12b-Chat-2602-Q3_K_L-GGUF:Q3_K_L --mmproj ./mmproj-google_gemma-3-12b-it-bf16.gguf -p "你是一個來自台灣的 AI 助手..." -cnv

🦙 Ollama 教學

建立一個名為 Modelfile 的檔案。
將下方提供的內容複製進去。

FROM ./Gemma-3-TAIDE-12b-Chat-2602-Q3_K_L.gguf
FROM ./mmproj-google_gemma-3-12b-it-bf16.gguf
SYSTEM """你是一個來自台灣的 AI 助手，你的名字是 TAIDE，由國家科學及技術委員會開發。你負責協助使用者解決問題，並以繁體中文 (zh-TW) 進行回答。"""

執行指令：

ollama create gemma-3-taide-12b-chat-2602-Q3_K_L -f Modelfile
ollama run gemma-3-taide-12b-chat-2602-Q3_K_L

📱 Nexa SDK CLI 教學

安裝指南: 請至 Nexa SDK GitHub 查閱最新版本的下載與安裝說明。
執行指令:

nexa infer gn00029914/Gemma-3-TAIDE-12b-Chat-2602-Q3_K_L-GGUF

🦀 Shimmy 教學

安裝指南: 請至 Shimmy GitHub 查閱最新版本的下載與安裝說明。
執行指令:

shimmy serve

Downloads last month: 140

GGUF

Model size

13B params

Architecture

gemma3

Hardware compatibility

3-bit

Model tree for gn00029914/Gemma-3-TAIDE-12b-Chat-2602-Q3_K_L-GGUF

Base model

taide/Gemma-3-TAIDE-12b-Chat-2602

Quantized

(7)

this model